Video AI models in Mixer AI

A short scene with both picture and sound in mind, from rustling fabric to a character's line.

Multiple shots, reference-based characters and optional sound for scenes that need more than an attractive camera move.

A clip of up to 30 seconds from text and references or from a chain of keyframes: named characters, voice samples and exact frames.

A lighter Kling 4.0: clips of 3–20 seconds in 720p from text and references, or from a start frame.

A short scene you can hear: a line of dialogue, footsteps, rainfall or room ambience.

Build a short story, not just a moving picture: up to 30 seconds, recurring characters, your own references and sound.

A short scene with your character, motion and sound, with Mini, Fast and Pro versions to choose from.

One subject, one action, one short clip, from text or a starting image.

Turn a photo into a short moving shot, or start from text with Master.

One moving shot lasting 3–15 seconds, without configuring a multi-scene sequence or character set.

A photo supplies the character; a video supplies the performance, from dance to conversational gestures.

Transfer a recorded performance to your character and choose which source supplies the background.

A speaking or singing portrait from one photo and a finished audio track.

A speaking or singing portrait from one photo and finished audio: Standard in 720p and Pro in 1080p.

A talking avatar from one photo and your audio recording: 720p video as long as the audio.

Animate a frame, try several ideas and build a clip lasting 6–30 seconds.

A short scene with sound, from text, a starting image or a set of photos.

Build a scene from separate references for appearance, movement and sound.

Create a short scene or transform footage you already have, choosing the version and input that fit.

Gemini Omni 1.1 Flash combines text, references, first/last frames, and video transformation in one variant.

Gemini Omni 1.0 Flash generates from text or references and can transform a short source-video segment.

Animate a finished illustration or photo with restrained or more active motion.

A scene up to 30 seconds long, combining photos, motion and audio references in one request.

Enlarge a clip you have already selected without generating the scene again.

Video from text, frames and references, editing and extension.

Turns a video into a depth map for editing and generation. Up to 2400 frames; preserves frame size up to 1080p.

Animates a portrait to a prepared audio track with synchronized speech and movement.

Creates videos with sound from a text prompt or a single source image.